1 September 1990 Self-organizing optical neural network for unsupervised learning
Author Affiliations +
Optical Engineering, 29(9), (1990). doi:10.1117/12.55702
One of the features in neural computing must be the ability to adapt to a changeable environment and to recognize unknown objects. This paper deals with an adaptive optical neural network using Kohonen's self-organizing feature map algorithm for unsupervised learning. A compact optical neural network of 64 neurons using liquid crystal televisions is used for this study. To test the performance of the self-organizing neural network, experimental demonstrations and computer simulations are provided. Effects due to unsupervised learning parameters are analyzed. We show that the optical neural network is capable of performing both unsupervised learning and pattern recognition operations simultaneously, by setting two matching scores in the learning algorithm. By using a slower learning rate, the construction of the memory matrix becomes more organized topologically. Moreover, the introduction of forbidden regions in the memory space enables the neural network to learn new patterns without erasing the old ones.
Thomas Taiwei Lu, Francis T. S. Yu, Don A. Gregory, "Self-organizing optical neural network for unsupervised learning," Optical Engineering 29(9), (1 September 1990). http://dx.doi.org/10.1117/12.55702

Neural networks

Machine learning


Detection and tracking algorithms

Evolutionary algorithms


Optical pattern recognition


Interferometry following adaptive optics
Proceedings of SPIE (October 20 2004)
Printed Arabic document recognition system
Proceedings of SPIE (January 17 2005)
Fractal character of turbulence-degraded wavefronts
Proceedings of SPIE (August 13 1993)
Light-sheet optimization for microscopy
Proceedings of SPIE (March 15 2016)

Back to Top